Machine learning-enabled enhanced sampling and ultra-fast molecular simulators

Andrew Ferguson (U of Chicago)

Jul 15. 2022, 09:45 — 10:30

Data-driven modeling and deep learning present powerful tools that are opening up new paradigms and opportunities in the understanding, discovery, and design of soft and biological materials. First, I will describe our use of autoencoding neural networks to learn data-driven collective variables in molecular systems and drive enhanced sampling within interleaved rounds of variable discovery and biased calculations. Second, I will describe an approach based on latent space simulators to learn ultra-fast surrogate models of molecular systems by stacking three specialized deep learning networks to (i) encode a molecular system into a slow latent space, (ii) propagate dynamics in this latent space, and (iii) generatively decode a synthetic molecular trajectory.

Further Information
ESI Boltzmann Lecture Hall
Associated Event:
ESI-DCAFM-TACO-VDSP Summer School on "Machine Learning for Materials Hard and Soft" (Graduate School)
Christoph Dellago (U of Vienna)
Ulrike Diebold (TU Vienna)
Leticia Gonzalez Herrero (U of Vienna)
Jani Kotakoski (U of Vienna)
Christiane Losert-Valiente Kroon (U of Vienna)